SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions

• URL: http://arxiv.org/abs/2607.18290v1
• Date: Tue, 30 Jun 2026 15:31:59 GMT
• Title: SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions
• Abstract summary: Kolmogorov-Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scientific computing tasks.<n>We present SechKAN, a KAN architecture based on hyperbolic secant (sech) functions.<n> Experimental results indicate the effectiveness of SechKAN in function fitting, PDE problems, and image classification tasks.
• Score: 0.8168419766775443
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In recent years, Kolmogorov-Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scientific computing tasks, offering a new paradigm for neural network design. In this paper, we present SechKAN, a KAN architecture based on hyperbolic secant (sech) functions. The hyperbolic secant basis is used for its smooth bell-shaped form, localized responses, and stable gradients. We employ 1D linear transformations to reduce the number of parameters, allowing SechKAN to remain comparable to multilayer perceptrons (MLPs) in model size. Experimental results indicate the effectiveness of SechKAN in function fitting, PDE problems, and image classification tasks on benchmark datasets, including MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. SechKAN achieves superior performance compared to MLPs and other KAN variants while maintaining a similar number of parameters. However, its running time, while better than that of other KAN variants, is slightly longer than that of MLPs.

Related papers

• Kolmogorov Arnold networks (KAN) for aerodynamic prediction: a comparison with MLPs and GNNs [2.9921589115206273]
  Kolmogorov Arnold networks (KAN) have recently been introduced as a neural network architecture whose trainable parameters adapt the activation functions.<n>Here we assess the performance of KANs --and its comparison against graph neural networks (GNNs) in the realm of fluid dynamics modelling.
  arXiv  Detail & Related papers  (2026-06-25T15:02:04Z)
• FEKAN: Feature-Enriched Kolmogorov-Arnold Networks [0.34376560669160394]
  Kolmogorov-Arnold Networks (KANs) have emerged as a compelling alternative to multilayer perceptrons.<n>FEKAN is a simple yet effective extension that preserves all the advantages of KAN while improving computational efficiency and predictive accuracy.
  arXiv  Detail & Related papers  (2026-02-18T15:17:55Z)
• Improving Memory Efficiency for Training KANs via Meta Learning [55.24089119864207]
  We propose to generate weights for KANs via a smaller meta-learner, called MetaKANs.<n>By training KANs and MetaKANs in an end-to-end differentiable manner, MetaKANs achieve comparable or even superior performance.
  arXiv  Detail & Related papers  (2025-06-09T08:38:26Z)
• AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning [4.843466576537832]
  Kolmogorov-Arnold Networks (KANs) have inspired numerous works exploring their applications across a wide range of scientific problems.<n>We introduce Activation Function-Based Kolmogorov-Arnold Networks (AF-KAN), expanding ReLU-KAN with various activations and their function combinations.<n>This novel KAN also incorporates parameter reduction methods, primarily attention mechanisms and data normalization, to enhance performance on image classification datasets.
  arXiv  Detail & Related papers  (2025-03-08T07:38:51Z)
• Low Tensor-Rank Adaptation of Kolmogorov--Arnold Networks [70.06682043272377]
  Kolmogorov--Arnold networks (KANs) have demonstrated their potential as an alternative to multi-layer perceptions (MLPs) in various domains.<n>We develop low tensor-rank adaptation (LoTRA) for fine-tuning KANs.<n>We explore the application of LoTRA for efficiently solving various partial differential equations (PDEs) by fine-tuning KANs.
  arXiv  Detail & Related papers  (2025-02-10T04:57:07Z)
• PRKAN: Parameter-Reduced Kolmogorov-Arnold Networks [47.947045173329315]
  Kolmogorov-Arnold Networks (KANs) represent an innovation in neural network architectures.<n>KANs offer a compelling alternative to Multi-Layer Perceptrons (MLPs) in models such as CNNs, RecurrentReduced Networks (RNNs) and Transformers.<n>This paper introduces PRKANs, which employ several methods to reduce the parameter count in layers, making them comparable to Neural M layers.
  arXiv  Detail & Related papers  (2025-01-13T03:07:39Z)
• Incorporating Arbitrary Matrix Group Equivariance into KANs [69.30866522377694]
  Kolmogorov-Arnold Networks (KANs) have seen great success in scientific domains.<n>We propose Equivariant Kolmogorov-Arnold Networks (EKAN) to broaden their applicability to more fields.
  arXiv  Detail & Related papers  (2024-10-01T06:34:58Z)
• A preliminary study on continual learning in computer vision using Kolmogorov-Arnold Networks [43.70716358136333]
  Kolmogorov- Networks (KAN) are based on a fundamentally different mathematical framework. KANs address several major issues insio, such as forgetting in continual learning scenarios. We extend the investigation by evaluating the performance of KANs in continual learning tasks within computer vision.
  arXiv  Detail & Related papers  (2024-09-20T14:49:21Z)
• Kolmogorov-Arnold Transformer [72.88137795439407]
  We introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces layers with Kolmogorov-Arnold Network (KAN) layers. We identify three key challenges: (C1) Base function, (C2) Inefficiency, and (C3) Weight. With these designs, KAT outperforms traditional-based transformers.
  arXiv  Detail & Related papers  (2024-09-16T17:54:51Z)
• Kolmogorov-Smirnov GAN [52.36633001046723]
  We propose a novel deep generative model, the Kolmogorov-Smirnov Generative Adversarial Network (KSGAN) Unlike existing approaches, KSGAN formulates the learning process as a minimization of the Kolmogorov-Smirnov (KS) distance.
  arXiv  Detail & Related papers  (2024-06-28T14:30:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.